Open WebUI
Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.
QuickDrop
QuickDrop functions as an ephemeral, self-hosted file distribution node and pastebin that eliminates account requirements for rapid data transfers. Users can drag individual files, paste plain text code snippets, or drop entire folder structures while preserving complete directory hierarchies through automated client manifests. Resumable chunked transfers split multi-gigabyte payloads into resilient blocks, ensuring dependable uploads over unstable network connections. Senders can protect sensitive documents with optional AES encryption at rest, individual passphrase requirements, and automatic metadata stripping that removes GPS coordinates and camera EXIF markers. Granular share token policies restrict access by enforce maximum download quotas, burn-after-reading limits, or strict calendar expiration timestamps. In-browser viewers generate instant previews for code syntax, Markdown documentation, PDF reports, audio tracks, and high-resolution images without downloading files locally. Built-in QR code generators allow mobile devices to retrieve shared payloads instantly across local wireless networks. System operators can govern storage lifecycles through an administrative control panel with configurable retention windows, automated background garbage collection, and custom storage caps. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Paqet
Most proxies ask the operating system nicely for a socket; paqet skips the conversation, building its own TCP packets byte by byte to tunnel traffic between your machine and your server. The server end listens on a port you choose and speaks only in raw packets it crafts and captures itself through pcap, before the kernel's connection tracking ever sees them. On your machine, the client presents an ordinary SOCKS5 proxy on localhost plus optional port forwards, so browsers and command-line tools connect exactly as they would to any proxy. Between the two ends, KCP with smux multiplexing turns a stream of self-contained packets into fast, reliable, encrypted sessions, with AES or lighter modes selected per deployment. TCP flag cycling varies how packets present themselves on the wire, giving operators control over the traffic pattern the tunnel produces. Built-in utilities generate the shared secret, ping the server with a single test packet, and dump live traffic decoded, so a silent tunnel gets diagnosed in minutes rather than by packet-capture archaeology. One YAML file per side declares the role, network interface, gateway MAC, and keys, and the same binary runs both ends. It suits security research, hostile networks, and anyone whose ordinary proxies keep getting reset. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
HitKeep
HitKeep is a sovereign web analytics platform that consolidates cookieless visitor telemetry, conversion funnels, e-commerce revenue reports, and AI engine visibility into a privacy-respecting dashboard that replaces Google Analytics and complex tracking clouds. Marketing teams can monitor inbound visitor journeys without installing intrusive consent banners or violating regional GDPR regulations. Custom conversion funnels and goal milestones track user registrations, checkout transactions, newsletter subscriptions, and software downloads with exact revenue attribution. Integrated Google Search Console synchronization brings organic search queries, keyword impression rankings, and click-through metrics directly alongside real-time pageview logs. A dedicated artificial intelligence visibility dashboard monitors crawling bots, retrieval citations, and direct referral visits originating from ChatGPT, Claude, Perplexity, and other generative search agents. Growth analysts can pose natural language questions to an embedded AI reporting assistant, generating instant cohort breakdowns and engagement trends without assembling complex manual filters. Site operators can configure custom tracking domains, whitelist reverse proxy networks, filter out referrer spam, and schedule automated database backups across persistent storage volumes. Complete data sovereignty controls allow teams to export raw event telemetry into open Parquet and CSV archives or stream metrics into external business intelligence warehouses via webhooks. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Nod
Nod is a personal AI assistant with its own computer, so you can hand it an errand like chasing an unpaid invoice or cancelling a trial and watch it finish the job on real websites. One ongoing conversation follows you from the browser to Telegram and WhatsApp, and long jobs become saved tasks with live status lines on a Scheduled page. Connect Gmail, Calendar, Slack, Notion, Linear, or an n8n instance, and it reads threads, drafts the replies you owe, and prepares a one-page brief before each call. Every action that could change something is checked against your rules, and anything uncovered waits for your yes. Passwords, codes, and cards sit in a Vault that the server types into websites, so the model never sees them. Memory notes are visible, editable, and tied to the message they came from. Schedules run recurring checks like a weekly recap or a price watch that speaks up only on change. Usage lists every action with costs and a monthly spending limit. Pick OpenAI, Anthropic, Gemini, OpenRouter, Bedrock, or a local Ollama server as the model. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Morphic
Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.
Plausible
Built as a direct rejection of the adtech model, Plausible is the best-known privacy-first web analytics tool - lightweight, cookie-free, and open-source. It sets no cookies and stores no personal data: unique visitors are counted via a hash of IP plus User-Agent that rotates every 24 hours and is never stored raw, so no consent banner is required and GDPR compliance is structural rather than contractual. The tracking script is under 1 KB - orders of magnitude lighter than GA - and the dashboard is a deliberate contrast to GA4's sprawl: one fast-loading page with visitors, sources, top pages, countries, devices, and UTM breakdowns, filterable by any dimension. Custom events and goals track signups and clicks, Google Search Console integration pulls in search queries, scheduled email reports keep stakeholders updated, and the Stats API (v2) plus CSV export feed data anywhere. This is the AGPL-licensed Community Edition, the same Elixir codebase that powers Plausible's cloud service, running as three containers: the web app, PostgreSQL for accounts, and ClickHouse for event storage - which means self-hosters get direct SQL access to raw analytics data the cloud version never exposes. Traffic data stays entirely on your server, with no visitor caps or per-pageview pricing.
Medama
Track website traffic and conversion funnels with sub-second precision while guaranteeing visitors total anonymity with Medama, a privacy-first web analytics platform operating without cookies, IP storage, or consent banners. Site owners embed a sub-kilobyte tracking script into web headers to record page views, session duration, referrers, screen resolutions, browser user agents, and geographic countries anonymously. Built-in caching header mechanisms determine unique daily visitors without generating persistent hashes or storing cross-site identifiers that violate privacy regulations. The web dashboard visualizes hourly traffic trends with interactive area charts and provides multi-dimensional data tables breaking down top-performing pages, search engine referrers, operating systems, and campaign UTM parameters. Developers can instrument custom click events and page attributes using simple HTML data attributes to measure conversions, document downloads, button interactions, and user subscription states. Administrators manage multiple websites from a single interface, configure curated anti-spam blocklists using Firehol and Tor exit node feeds, and monitor server CPU, memory, and disk usage in real time. Full OpenAPI specification endpoints allow teams to export analytics data directly into internal business intelligence pipelines and custom executive dashboards. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Usermemos
Memos, the lightweight open-source note service from the usememos project, packaged as a containerized deployment for multi-architecture Docker hosts (x86-64 and arm64): that is Usermemos. The model is frictionless capture: no folders or titles, just a chronological stream of Markdown notes with code blocks, task lists, tables, and file attachments, organized by #hashtags pulled automatically from the text. Per-memo visibility - private, protected for logged-in users, or public - lets a single instance serve as a personal journal, a shared team log, or a public microblog simultaneously. Multi-user support with authentication makes it workable for small teams, and full REST and gRPC APIs open capture and retrieval to CLIs, bots, and automation tools. The runtime is a single Go binary with a React frontend that idles around 50 MB of memory and stores content as plain Markdown in SQLite by default, with MySQL and PostgreSQL available for heavier deployments. Configuration happens through environment variables, access works over HTTP or HTTPS behind a reverse proxy, and there is no telemetry - notes stay on your server in a portable format.
Reactive Resume
With over 38,000 GitHub stars, nearly one million registered users, and over 1.3 million resumes created, Reactive Resume delivers a professional resume creation experience that rivals commercial platforms like Resume.io and Zety without collecting user data, showing advertisements, or imposing paywall restrictions. The real-time WYSIWYG editor renders changes instantly as users type, providing immediate visual feedback across all resume sections including work experience, education, skills, certifications, projects, and custom sections with typed extensions. Over fifteen professionally designed templates with full color customization, font selection, spacing adjustment, and icon style selectors ensure each resume reflects individual style preferences. The drag-and-drop system lets users move items between sections and pages freely across multi-column and full-width layouts. PDF generation produces pixel-perfect documents using a headless Chromium rendering pipeline, ensuring consistent output across all devices and print settings. Multi-language support covers over twenty languages with RTL script handling for Arabic and Hebrew. Authentication supports passkeys and multiple OAuth providers via Better Auth, while self-hosted deployment runs via Docker Compose with PostgreSQL and Browserless for PDF rendering. The import system accepts JSON Resume format, LinkedIn data exports, and PDF/DOCX files when AI integration is configured. AI-powered content suggestions using OpenAI, Google Gemini, Anthropic Claude, or local Ollama models help improve bullet points and professional summaries. A CSS editor with autocompletion allows fine-grained styling control. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Matomo
Several EU data protection authorities have ruled Google Analytics deployments unlawful; Matomo (formerly Piwik) is the most complete open-source replacement - a full analytics platform with 30+ report types across visitors, actions, referrers, goals, and ecommerce. The self-hosted PHP/MySQL edition is free and keeps every byte of visitor data on your infrastructure, which matters more each year: several EU data protection authorities have ruled Google Analytics deployments unlawful, while Matomo configured for cookieless tracking is approved by France's CNIL for use without a consent banner. All reporting runs on 100% unsampled data - no extrapolation at high traffic volumes. The GDPR Manager handles data subject requests and deletion, with IP anonymization, retention controls, and Do Not Track support built in. A dedicated importer pulls your historical Google Analytics data so years of trends survive the migration. Core analytics cover campaigns, custom variables and dimensions, entry/exit pages, downloads, site search, and full ecommerce tracking with a comprehensive HTTP API for reporting and ingestion. Premium plugins extend the platform into Hotjar-class behavioral tooling - click and scroll heatmaps, session recordings, conversion funnels, form analytics, A/B testing - plus a tag manager and SAML SSO. For teams that need GA-equivalent depth with actual data ownership, Matomo is the realistic drop-in replacement.
Ovumcy
Your cycle history is among the most personal data you will ever record, and Ovumcy keeps it on a server you control instead of a tracker's cloud. Log period days, flow intensity, symptoms, and free-form notes in seconds from any browser, and define your own custom symptoms when the preset list misses something you feel. The calendar view lays out your month with predicted period, ovulation, and fertile-window days marked, while statistics views surface cycle length trends and patterns across months. Predictions come from your own logged history, refined when temperature or cervical-mucus entries sharpen the estimate. Reminders reach you three ways: a dashboard banner before an expected period, a webhook ping to your own ntfy or Gotify server, or a private read-only calendar subscription that drops estimates into the calendar app you already use. Install it to your phone home screen and it opens like a native app, in English, Russian, Spanish, French, German, or Italian. Export the full history as CSV or JSON whenever you want a backup or a change of tools. Optional OIDC sign-in and TOTP two-factor authentication protect access, and the app makes no analytics or telemetry calls at all. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.
Joplin
Notes on Windows, macOS, Linux, Android, iOS, and the terminal, synced through your own server: Joplin pairs its open-source clients with Joplin Server, the official self-hosted backend that replaces Dropbox, OneDrive, or Nextcloud as the synchronization target. Notes are Markdown with inline attachments (images, PDFs, audio), organized into hierarchical notebooks and sub-notebooks with cross-cutting tags, alongside to-do lists with reminders and alarms. End-to-end encryption is the headline feature: enabled in the clients, it encrypts sync payloads on-device before upload, so the server stores blobs it cannot read - genuine protection even if the host is compromised. The desktop app offers both Rich Text and Markdown editors, extended by a plugin ecosystem, custom themes, and an Extension API for writing your own scripts; a Web Clipper for Chrome and Firefox captures full pages or screenshots straight into notebooks. Joplin Server ships as a Docker image with SQLite for evaluation and PostgreSQL for production, offers a filesystem storage driver for large content, and includes multi-user support and note sharing - all free under AGPL-3.0 when self-hosted. Notes stay in an open format, so the exit path always exists.
GoatCounter
GoatCounter delivers meaningful web traffic insights — pageviews, referrers, browsers, screen sizes, country-level geolocation — without setting a single cookie, without collecting personal data, and without forcing GDPR consent banners on your visitors. Written entirely in Go and distributed as a single compiled binary consuming roughly 25MB of RAM, it adds just 3.5KB to your pages via the tracking script, with a JavaScript-free tracking pixel alternative for sites that avoid scripts entirely, plus backend middleware integration and log file import for server-side collection. The dashboard displays pageview counts per path with hourly resolution, referrer sources grouped by domain with full URL on hover, browser and OS version breakdowns, screen size distributions, and country-level location data derived from IP addresses that are immediately discarded after geolocation. Campaign tracking supports UTM parameters and custom data attributes. A public stats option exposes your dashboard at a shareable URL for build-in-public transparency. SQLite serves as the default database requiring zero administration, while PostgreSQL handles higher-traffic deployments with multi-site setups. Built-in ACME and TLS certificate management eliminates reverse proxy requirements for HTTPS — no Nginx or Caddy needed. The REST API provides programmatic access to all analytics data. Deploy as a single binary, via Docker with the official arp242/goatcounter image, or through native packages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. EUPL-1.2 licensed.
Odysseus
Agents with tool use, deep research, a document editor, an IMAP/SMTP email client with AI triage, notes, tasks, and a CalDAV-synced calendar - Odysseus bundles all of it into one open-source, self-hosted AI workspace. It runs local models through Ollama, vLLM, or llama.cpp and cloud APIs like OpenAI and OpenRouter, with a hardware-aware Cookbook that scans your machine and recommends quantized models that fit. Persistent memory uses ChromaDB with hybrid vector-plus-keyword retrieval, web search runs through a bundled SearXNG instance, and agents can use MCP servers, files, and shell access with safety controls, plus custom skills and scheduled agent tasks. A blind Compare mode runs side-by-side model duels with identities hidden and accumulates Elo-style ratings from your votes, so model selection is based on your actual workloads rather than leaderboard claims. Deep research mode - adapted from the Tongyi DeepResearch approach - reads sources through SearXNG and produces cited reports, while the email client tags, summarizes, sets reminders, and drafts replies locally rather than through a third-party mail AI. The writing-first document editor adds AI edits, Markdown and HTML support, and version history. The stack is Python 3.11 with FastAPI, SQLite for state, and a vanilla JS frontend, licensed AGPL-3.0 with zero telemetry. Because agents can read email and execute commands, keep authentication enabled and never expose it as a public unauthenticated service.
Betterlytics
Page views, funnels, session replays, error reports, Core Web Vitals, and uptime checks share one cookieless dashboard in Betterlytics, so teams stop stitching several tools together. The overview charts visitors, page views, bounce rate, and visit duration against the previous period, and annotations mark launches or campaigns right on the timeline. Breakdowns cover referrers, channels, UTM campaigns, browsers, devices, and operating systems, with visitor locations on a world map once an optional MaxMind key is added. Custom events, global properties such as plan or app version, and outbound link tracking show what visitors actually do, while user journey diagrams and funnels reveal where they drift away. Session replay is opt-in per tracking script, masks text and form inputs by default, and can keep recordings in your own S3-compatible bucket. Error tracking groups JavaScript errors with stack traces, a session trail, and a link to the matching replay. Uptime and SSL monitors alert through Slack, Discord, Teams, or webhooks and feed public status pages on your own domain. Teammates join by invitation, two-factor login is available, and a built-in MCP server lets Claude, Cursor, or Codex answer traffic questions. A script of about 3.5 KB or a WordPress plugin handles installation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.
Plainpad
Notes are personal, and Plainpad keeps them that way by running entirely on your own server instead of a vendor cloud. Class notes, trip plans, lyrics, and side-project ideas sit in one fast list that searches instantly and opens in any modern browser, adapting to phones, tablets, and desktops. Added to a home screen it launches like an app, and offline editing keeps writing possible when the connection drops. Turning on encryption stores titles and content encrypted at rest, so even database access does not expose what you wrote. One installation supports unlimited accounts with administrator and user roles, and every person keeps a private notebook no one else can read. There are no note limits, no device limits, no ads, and no tracking of any kind. Moving in is scripted through the built-in REST API, which can import collections from files and other note services into the right accounts. The stack asks only for PHP and MySQL, or a single Docker Compose command, and a sample data seeder can populate a fresh install with realistic study notes for evaluation. Simplicity is the design goal: the interface stays quiet, loads quickly, and leaves the words in front. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL 3.0 licensed.
Farfalle
Live web search plus an LLM of your choice: Farfalle is an open-source, self-hosted answer engine in the Perplexity mold. Queries route through one of several search providers - self-hosted SearXNG for a fully independent stack, or Tavily, Serper, and Bing APIs - and the model composes a cited answer from the retrieved results. Model flexibility is the core design: run llama3, mistral, gemma, or phi3 locally through Ollama for zero per-query cost and full privacy, use cloud models like GPT-4o or Groq-hosted Llama 3 for speed, or route to any provider via LiteLLM. An Expert Search mode uses an agent that plans a multi-step search strategy and executes it for harder questions, and chat history keeps prior research sessions available. The stack is a Next.js and shadcn/ui frontend over a FastAPI backend with Redis rate limiting, shipped as a pre-built Docker image. A browser search-engine entry pointing at your instance makes it the default search from the address bar. Paired with SearXNG and Ollama, the whole pipeline runs with no external API at all.